Understand it,
don't memorize it.
A community-built path through hard subjects, taught visually and from the ground up, without skipping a single brick. Every idea holds as many explanations as people have written, because the one that finally makes it click is different for everyone.
The Path to Machine Learning
Start with arrows on a grid. End understanding how a machine learns. Every step earns the next; no brick is skipped.
-
1
Linear Algebra 22 concepts · start here
Data is vectors and models are transformations. This is the ground everything else stands on.
-
2
Calculus planned 8 topics planned · see the roster
The math of change. A model learns by asking how a tiny nudge to its knobs changes its error.
-
3
Probability planned 8 topics planned · see the roster
The math of uncertainty. Real data is noisy, and models reason in odds, not certainties.
-
4
Optimization planned 7 topics planned · see the roster
Learning is finding the lowest point of an error surface. This is how you get there.
needs first: Calculus, Linear Algebra
-
5
Statistics planned 7 topics planned · see the roster
How to trust what data says, and how to catch a model that has fooled itself.
needs first: Probability
-
6
Machine Learning planned 9 topics planned · see the roster
The destination. Every domain before it was already walking here.
needs first: Linear Algebra, Calculus, Probability, Optimization, Statistics
No missing bricks
No concept assumes something you were never taught. Every prerequisite is a link, and it exists, checked automatically on every contribution. A roadmap with a missing brick is not a roadmap; it is a trap. The greyed steps above are the plan, waiting for someone to build them. Click any of them to see its full roster of planned topics.
Want a subject that is not here?
Cryptography, signals, compilers, graphics. The path to machine learning is the first track, not the only one. Propose a domain and it goes on the board for anyone to build.